Hugging Face's logo

Z3K3
/
punk-music-test

Text-to-Audio
PEFT
Safetensors
musicgen
ylacombe/tiny-punk
Generated from Trainer
Model card Files Community
Z3K3 commited on
Commit
5808771
·
verified ·
1 Parent(s): 1ff559a

End of training

Browse files
Files changed (5) hide show
  1. README.md +4 -2
  2. all_results.json +15 -0
  3. eval_results.json +9 -0
  4. train_results.json +9 -0
  5. trainer_state.json +273 -0
README.md CHANGED
@@ -3,6 +3,8 @@ base_model: facebook/musicgen-large
3
  library_name: peft
4
  license: cc-by-nc-4.0
5
  tags:
 
 
6
  - generated_from_trainer
7
  model-index:
8
  - name: punk-music-test
@@ -14,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # punk-music-test
16
 
17
- This model is a fine-tuned version of [facebook/musicgen-large](https://huggingface.co/facebook/musicgen-large) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
  - Loss: 4.6589
20
- - Clap: 0.0539
21
 
22
  ## Model description
23
 
 
3
  library_name: peft
4
  license: cc-by-nc-4.0
5
  tags:
6
+ - text-to-audio
7
+ - ylacombe/tiny-punk
8
  - generated_from_trainer
9
  model-index:
10
  - name: punk-music-test
 
16
 
17
  # punk-music-test
18
 
19
+ This model is a fine-tuned version of [facebook/musicgen-large](https://huggingface.co/facebook/musicgen-large) on the YLACOMBE/TINY-PUNK - DEFAULT dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 4.6589
22
+ - Clap: 0.0487
23
 
24
  ## Model description
25
 
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.857142857142857,
3
+ "eval_clap": 0.04868295416235924,
4
+ "eval_loss": 4.658874988555908,
5
+ "eval_runtime": 211.9045,
6
+ "eval_samples": 8,
7
+ "eval_samples_per_second": 0.038,
8
+ "eval_steps_per_second": 0.038,
9
+ "total_flos": 22951666441296.0,
10
+ "train_loss": 8.58632747332255,
11
+ "train_runtime": 1809.0113,
12
+ "train_samples": 54,
13
+ "train_samples_per_second": 0.239,
14
+ "train_steps_per_second": 0.013
15
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.857142857142857,
3
+ "eval_clap": 0.04868295416235924,
4
+ "eval_loss": 4.658874988555908,
5
+ "eval_runtime": 211.9045,
6
+ "eval_samples": 8,
7
+ "eval_samples_per_second": 0.038,
8
+ "eval_steps_per_second": 0.038
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.857142857142857,
3
+ "total_flos": 22951666441296.0,
4
+ "train_loss": 8.58632747332255,
5
+ "train_runtime": 1809.0113,
6
+ "train_samples": 54,
7
+ "train_samples_per_second": 0.239,
8
+ "train_steps_per_second": 0.013
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,273 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.857142857142857,
5
+ "eval_steps": 50.0,
6
+ "global_step": 24,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2857142857142857,
13
+ "grad_norm": 0.14930766820907593,
14
+ "learning_rate": 9.583333333333334e-05,
15
+ "loss": 8.9408,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.5714285714285714,
20
+ "grad_norm": 0.12185841798782349,
21
+ "learning_rate": 9.166666666666667e-05,
22
+ "loss": 8.8871,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.8571428571428571,
27
+ "grad_norm": 0.22343124449253082,
28
+ "learning_rate": 8.75e-05,
29
+ "loss": 8.875,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.8571428571428571,
34
+ "eval_clap": 0.067754365503788,
35
+ "eval_loss": 4.407386302947998,
36
+ "eval_runtime": 209.2468,
37
+ "eval_samples_per_second": 0.038,
38
+ "eval_steps_per_second": 0.038,
39
+ "step": 3
40
+ },
41
+ {
42
+ "epoch": 1.1428571428571428,
43
+ "grad_norm": 0.302925169467926,
44
+ "learning_rate": 8.333333333333334e-05,
45
+ "loss": 8.8616,
46
+ "step": 4
47
+ },
48
+ {
49
+ "epoch": 1.4285714285714286,
50
+ "grad_norm": 0.30731210112571716,
51
+ "learning_rate": 7.916666666666666e-05,
52
+ "loss": 8.8302,
53
+ "step": 5
54
+ },
55
+ {
56
+ "epoch": 1.7142857142857144,
57
+ "grad_norm": 0.35163554549217224,
58
+ "learning_rate": 7.500000000000001e-05,
59
+ "loss": 8.7832,
60
+ "step": 6
61
+ },
62
+ {
63
+ "epoch": 2.0,
64
+ "grad_norm": 0.40824490785598755,
65
+ "learning_rate": 7.083333333333334e-05,
66
+ "loss": 8.7074,
67
+ "step": 7
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_clap": 0.05861677974462509,
72
+ "eval_loss": 4.424124717712402,
73
+ "eval_runtime": 209.036,
74
+ "eval_samples_per_second": 0.038,
75
+ "eval_steps_per_second": 0.038,
76
+ "step": 7
77
+ },
78
+ {
79
+ "epoch": 2.2857142857142856,
80
+ "grad_norm": 0.5694748759269714,
81
+ "learning_rate": 6.666666666666667e-05,
82
+ "loss": 8.6684,
83
+ "step": 8
84
+ },
85
+ {
86
+ "epoch": 2.571428571428571,
87
+ "grad_norm": 0.4113900065422058,
88
+ "learning_rate": 6.25e-05,
89
+ "loss": 8.6663,
90
+ "step": 9
91
+ },
92
+ {
93
+ "epoch": 2.857142857142857,
94
+ "grad_norm": 0.4741291403770447,
95
+ "learning_rate": 5.833333333333334e-05,
96
+ "loss": 8.6372,
97
+ "step": 10
98
+ },
99
+ {
100
+ "epoch": 2.857142857142857,
101
+ "eval_clap": 0.0703531801700592,
102
+ "eval_loss": 4.461740493774414,
103
+ "eval_runtime": 217.2072,
104
+ "eval_samples_per_second": 0.037,
105
+ "eval_steps_per_second": 0.037,
106
+ "step": 10
107
+ },
108
+ {
109
+ "epoch": 3.142857142857143,
110
+ "grad_norm": 0.5966173410415649,
111
+ "learning_rate": 5.4166666666666664e-05,
112
+ "loss": 8.5292,
113
+ "step": 11
114
+ },
115
+ {
116
+ "epoch": 3.4285714285714284,
117
+ "grad_norm": 0.4768383204936981,
118
+ "learning_rate": 5e-05,
119
+ "loss": 8.5238,
120
+ "step": 12
121
+ },
122
+ {
123
+ "epoch": 3.7142857142857144,
124
+ "grad_norm": 0.5463787913322449,
125
+ "learning_rate": 4.5833333333333334e-05,
126
+ "loss": 8.5916,
127
+ "step": 13
128
+ },
129
+ {
130
+ "epoch": 4.0,
131
+ "grad_norm": 0.5644258856773376,
132
+ "learning_rate": 4.166666666666667e-05,
133
+ "loss": 8.5145,
134
+ "step": 14
135
+ },
136
+ {
137
+ "epoch": 4.0,
138
+ "eval_clap": 0.05660417675971985,
139
+ "eval_loss": 4.537668228149414,
140
+ "eval_runtime": 215.7023,
141
+ "eval_samples_per_second": 0.037,
142
+ "eval_steps_per_second": 0.037,
143
+ "step": 14
144
+ },
145
+ {
146
+ "epoch": 4.285714285714286,
147
+ "grad_norm": 0.4694964587688446,
148
+ "learning_rate": 3.7500000000000003e-05,
149
+ "loss": 8.446,
150
+ "step": 15
151
+ },
152
+ {
153
+ "epoch": 4.571428571428571,
154
+ "grad_norm": 0.5955868363380432,
155
+ "learning_rate": 3.3333333333333335e-05,
156
+ "loss": 8.5089,
157
+ "step": 16
158
+ },
159
+ {
160
+ "epoch": 4.857142857142857,
161
+ "grad_norm": 0.5509549975395203,
162
+ "learning_rate": 2.916666666666667e-05,
163
+ "loss": 8.4215,
164
+ "step": 17
165
+ },
166
+ {
167
+ "epoch": 4.857142857142857,
168
+ "eval_clap": 0.056698545813560486,
169
+ "eval_loss": 4.5900163650512695,
170
+ "eval_runtime": 209.8722,
171
+ "eval_samples_per_second": 0.038,
172
+ "eval_steps_per_second": 0.038,
173
+ "step": 17
174
+ },
175
+ {
176
+ "epoch": 5.142857142857143,
177
+ "grad_norm": 0.6947008967399597,
178
+ "learning_rate": 2.5e-05,
179
+ "loss": 8.4253,
180
+ "step": 18
181
+ },
182
+ {
183
+ "epoch": 5.428571428571429,
184
+ "grad_norm": 0.609464168548584,
185
+ "learning_rate": 2.0833333333333336e-05,
186
+ "loss": 8.4624,
187
+ "step": 19
188
+ },
189
+ {
190
+ "epoch": 5.714285714285714,
191
+ "grad_norm": 0.49679213762283325,
192
+ "learning_rate": 1.6666666666666667e-05,
193
+ "loss": 8.3189,
194
+ "step": 20
195
+ },
196
+ {
197
+ "epoch": 6.0,
198
+ "grad_norm": 0.6397719383239746,
199
+ "learning_rate": 1.25e-05,
200
+ "loss": 8.4121,
201
+ "step": 21
202
+ },
203
+ {
204
+ "epoch": 6.0,
205
+ "eval_clap": 0.03204277530312538,
206
+ "eval_loss": 4.638527870178223,
207
+ "eval_runtime": 216.9058,
208
+ "eval_samples_per_second": 0.037,
209
+ "eval_steps_per_second": 0.037,
210
+ "step": 21
211
+ },
212
+ {
213
+ "epoch": 6.285714285714286,
214
+ "grad_norm": 0.6107072830200195,
215
+ "learning_rate": 8.333333333333334e-06,
216
+ "loss": 8.3785,
217
+ "step": 22
218
+ },
219
+ {
220
+ "epoch": 6.571428571428571,
221
+ "grad_norm": 0.553840696811676,
222
+ "learning_rate": 4.166666666666667e-06,
223
+ "loss": 8.3048,
224
+ "step": 23
225
+ },
226
+ {
227
+ "epoch": 6.857142857142857,
228
+ "grad_norm": 0.5590672492980957,
229
+ "learning_rate": 0.0,
230
+ "loss": 8.377,
231
+ "step": 24
232
+ },
233
+ {
234
+ "epoch": 6.857142857142857,
235
+ "eval_clap": 0.053874481469392776,
236
+ "eval_loss": 4.658874988555908,
237
+ "eval_runtime": 216.879,
238
+ "eval_samples_per_second": 0.037,
239
+ "eval_steps_per_second": 0.037,
240
+ "step": 24
241
+ },
242
+ {
243
+ "epoch": 6.857142857142857,
244
+ "step": 24,
245
+ "total_flos": 22951666441296.0,
246
+ "train_loss": 8.58632747332255,
247
+ "train_runtime": 1809.0113,
248
+ "train_samples_per_second": 0.239,
249
+ "train_steps_per_second": 0.013
250
+ }
251
+ ],
252
+ "logging_steps": 1.0,
253
+ "max_steps": 24,
254
+ "num_input_tokens_seen": 0,
255
+ "num_train_epochs": 8,
256
+ "save_steps": 500,
257
+ "stateful_callbacks": {
258
+ "TrainerControl": {
259
+ "args": {
260
+ "should_epoch_stop": false,
261
+ "should_evaluate": false,
262
+ "should_log": false,
263
+ "should_save": true,
264
+ "should_training_stop": true
265
+ },
266
+ "attributes": {}
267
+ }
268
+ },
269
+ "total_flos": 22951666441296.0,
270
+ "train_batch_size": 4,
271
+ "trial_name": null,
272
+ "trial_params": null
273
+ }